LangChain: Streaming Bugs Squashed
Today we're celebrating a solid bug fix from jackjin1997 that tackles a tricky streaming issue with OpenAI function calls. The fix ensures namespace fields are properly preserved during streaming, preventing those frustrating 400 errors that were breaking tool_search workflows with defer_loading.
Duration: PT3M57S
Episode overview
This episode is a short developer briefing from LangChain.
It explains recent repository work in plain language.
- Show: LangChain
- Published: 2026-03-21T10:01:48Z
- Audio duration: PT3M57S
Transcript excerpt
This excerpt keeps the crawler page concise. Listen to the episode or use the RSS feed for the full update.
Hey there, fantastic developers! Welcome back to another episode of the LangChain podcast. I'm your host, and wow, do I have some good news for you today. If you've been wrestling with streaming function calls and mysterious 400 errors, today's episode is going to make your day so much better.
Let's dive right into our main story. We had one really solid pull request merge yesterday from jackjin1997, and this one's a perfect example of how the devil really is in the details when it comes to API integrations.
So here's what was happening. Picture this: you're working with OpenAI's function calling feature, specifically using tool_search with defer_loading. Everything works perfectly when you're not streaming, but the moment you switch to streaming mode, boom - 400 errors start flying around like confetti at a very sad…
The culprit? A sneaky little field called namespace that was getting dropped during the streaming process. Now, this is one of those bugs that really showcases the complexity of modern AI systems. The non-streaming path was doing everything right - it was using model_dump with exclude_none equals true, which…
This is actually a really common pattern in API work, and I…
Th…